Text Generation
Transformers
Safetensors
Russian
English
ppai
pacperlar
mixture-of-experts
russian
code
small-language-model
custom_code
Instructions to use AdminHugging/PP-Hydrogen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdminHugging/PP-Hydrogen with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdminHugging/PP-Hydrogen", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AdminHugging/PP-Hydrogen", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AdminHugging/PP-Hydrogen with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdminHugging/PP-Hydrogen" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminHugging/PP-Hydrogen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AdminHugging/PP-Hydrogen
- SGLang
How to use AdminHugging/PP-Hydrogen with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "AdminHugging/PP-Hydrogen" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminHugging/PP-Hydrogen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "AdminHugging/PP-Hydrogen" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminHugging/PP-Hydrogen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AdminHugging/PP-Hydrogen with Docker Model Runner:
docker model run hf.co/AdminHugging/PP-Hydrogen
Upload logs/metrics.csv with huggingface_hub
Browse files- logs/metrics.csv +40 -0
logs/metrics.csv
CHANGED
|
@@ -56,3 +56,43 @@ step,tokens,loss,lr,tok_s,vram_gb,elapsed_h
|
|
| 56 |
14925,550232064,2.59377,4.37e-04,24721,9.98,0.58
|
| 57 |
14950,551153664,2.92744,4.37e-04,24193,9.98,0.59
|
| 58 |
14975,552075264,2.94475,4.36e-04,24428,9.98,0.61
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
14925,550232064,2.59377,4.37e-04,24721,9.98,0.58
|
| 57 |
14950,551153664,2.92744,4.37e-04,24193,9.98,0.59
|
| 58 |
14975,552075264,2.94475,4.36e-04,24428,9.98,0.61
|
| 59 |
+
15000,552996864,2.60384,4.36e-04,24657,9.98,0.62
|
| 60 |
+
15025,553918464,2.51729,4.35e-04,24131,9.98,0.63
|
| 61 |
+
15050,554840064,3.03459,4.35e-04,23904,9.98,0.65
|
| 62 |
+
15075,555761664,3.06706,4.34e-04,24464,9.98,0.66
|
| 63 |
+
15100,556683264,3.05482,4.34e-04,24251,9.98,0.67
|
| 64 |
+
15125,557604864,3.05476,4.33e-04,23878,9.98,0.68
|
| 65 |
+
15150,558526464,3.10899,4.33e-04,24048,9.98,0.69
|
| 66 |
+
15175,559448064,2.90314,4.32e-04,24255,9.98,0.70
|
| 67 |
+
15200,560369664,2.66439,4.32e-04,24495,9.98,0.71
|
| 68 |
+
15225,561291264,2.59448,4.31e-04,24383,9.98,0.72
|
| 69 |
+
15250,562212864,3.04536,4.31e-04,24855,9.98,0.73
|
| 70 |
+
15275,563134464,2.50758,4.30e-04,24833,9.98,0.74
|
| 71 |
+
15300,564056064,2.61525,4.30e-04,24504,9.98,0.75
|
| 72 |
+
15325,564977664,2.79751,4.29e-04,24490,9.98,0.76
|
| 73 |
+
15350,565899264,2.98562,4.29e-04,24095,9.98,0.77
|
| 74 |
+
15375,566820864,2.44458,4.28e-04,24298,9.98,0.78
|
| 75 |
+
15400,567742464,2.52102,4.28e-04,24627,9.98,0.79
|
| 76 |
+
15425,568664064,2.86815,4.27e-04,24390,9.98,0.80
|
| 77 |
+
15450,569585664,2.66938,4.27e-04,24303,9.98,0.81
|
| 78 |
+
15475,570507264,2.66501,4.26e-04,23904,9.98,0.82
|
| 79 |
+
15500,571428864,2.50997,4.26e-04,24939,9.98,0.84
|
| 80 |
+
15525,572350464,2.89544,4.25e-04,24419,9.98,0.85
|
| 81 |
+
15550,573272064,2.89215,4.25e-04,24305,9.98,0.86
|
| 82 |
+
15575,574193664,2.86015,4.24e-04,24732,9.98,0.87
|
| 83 |
+
15600,575115264,2.86560,4.23e-04,24245,9.98,0.88
|
| 84 |
+
15625,576036864,2.80974,4.23e-04,24028,9.98,0.89
|
| 85 |
+
15650,576958464,2.82995,4.22e-04,24420,9.98,0.90
|
| 86 |
+
15675,577880064,2.50814,4.22e-04,24646,9.98,0.91
|
| 87 |
+
15700,578801664,2.74559,4.21e-04,24883,9.98,0.92
|
| 88 |
+
15725,579723264,2.99391,4.21e-04,24437,9.98,0.93
|
| 89 |
+
15750,580644864,2.76869,4.20e-04,24660,9.98,0.95
|
| 90 |
+
15775,581566464,2.96453,4.20e-04,23961,9.98,0.96
|
| 91 |
+
15800,582488064,2.83082,4.19e-04,24671,9.98,0.97
|
| 92 |
+
15825,583409664,2.89129,4.19e-04,23903,9.98,0.98
|
| 93 |
+
15850,584331264,2.39490,4.18e-04,24934,9.98,0.99
|
| 94 |
+
15875,585252864,2.96907,4.18e-04,24323,9.98,1.00
|
| 95 |
+
15900,586174464,2.85499,4.17e-04,24933,9.98,1.01
|
| 96 |
+
15925,587096064,2.81448,4.17e-04,24322,9.98,1.02
|
| 97 |
+
15950,588017664,2.62503,4.16e-04,23886,9.98,1.03
|
| 98 |
+
15975,588939264,3.02937,4.16e-04,24517,9.98,1.04
|